def mergeSingle(src):
if not os.path.isdir(src):
Log.w(Duokan.__name__, '[%s] is not a diractory, exit...' % (src, ))
return
path = os.path.split(src)
id = path[1]
destPath = os.path.join(path[0], id+'.pdf')
DuoPdf.clean(src)
DuoPdf.merge(destPath, src)
def mergeSingle(src):
if not os.path.isdir(src):
Log.w(Duokan.__name__,
'[%s] is not a diractory, exit...' % (src, ))
return
path = os.path.split(src)
id = path[1]
destPath = os.path.join(path[0], id + '.pdf')
DuoPdf.clean(src)
DuoPdf.merge(destPath, src)
def _getProxy(self):
self.host = ''
self.user = ''
self.pswd = ''
try:
self.host = self.conf.get(Config.KEY_PROXY, Config.KEY_PROXY_HOST)
self.user = self.conf.get(Config.KEY_PROXY, Config.KEY_PROXY_USER)
self.pswd = self.conf.get(Config.KEY_PROXY, Config.KEY_PROXY_PAWD)
except:
Log.w(self.TAG, 'read proxy failed')
traceback.print_exc()
def _getProxy(self):
self.host = ''
self.user = ''
self.pswd = ''
try:
self.host = self.conf.get(Config.KEY_PROXY, Config.KEY_PROXY_HOST)
self.user = self.conf.get(Config.KEY_PROXY, Config.KEY_PROXY_USER)
self.pswd = self.conf.get(Config.KEY_PROXY, Config.KEY_PROXY_PAWD)
except:
Log.w(self.TAG, 'read proxy failed')
traceback.print_exc()
def merge(dest, srcDir):
'''merge pdf files in srcDir'''
if os.path.exists(srcDir) and os.path.isdir(srcDir):
files = os.listdir(srcDir)
if len(files) > 0:
merger = PdfFileMerger()
for i,f in enumerate(files):
Log.i(DuoPdf.__name__, 'merge file [%s]' % (f, ))
filePath = os.path.join(srcDir, f)
if (os.path.isfile(filePath)):
try:
srcFileHdl = open(filePath, 'rb')
merger.merge(position=i, fileobj=srcFileHdl)
except:
Log.w(DuoPdf.__name__, 'merge [%s] failed' % (filePath))
traceback.print_exc()
else:
Log.i(DuoPdf.__name__, 'skip file [%s]' % (filePath,))
Log.i(DuoPdf.__name__, 'save to file [%s]...' % (dest, ))
destFileStream = file(dest, 'wb')
merger.write(destFileStream)
destFileStream.close()
Log.i(DuoPdf.__name__, 'done')
else:
Log.w(DuoPdf.__name__, 'no file in [%s] to merge' % (srcDir))
else:
Log.w(DuoPdf.__name__, 'dir [%s] not exist.' % (srcDir,))
def cleanAllInPath(self, srcDir):
if os.path.exists(srcDir) and os.path.isdir(srcDir):
files = os.listdir(srcDir)
num = len(files)
if num > 0:
for i, f in enumerate(files):
print '%d/%d: %s' % (i, num, f)
fileName = self.getCleanedFileName(f)
srcPath = os.path.join(srcDir, f)
destPath = os.path.join(srcDir, fileName)
if (os.path.isfile(srcPath)):
if self.isCleanedFile(srcPath):
print 'skip [%s]' % srcPath
elif self.hasCleaned(srcPath):
print 'skip [%s]' % srcPath
else:
try:
DuoPdf.cleanPdf(srcPath, destPath)
# print '%s -> ' % srcPath
# print destPath
except:
Log.w(DuoPdf.__name__, 'clean [%s] failed' % (srcPath))
traceback.print_exc()
else:
Log.i(DuoPdf.__name__, 'skip file [%s]' % (srcPath,))
else:
Log.w(DuoPdf.__name__, 'no file in [%s] to clean' % (srcDir))
else:
Log.w(DuoPdf.__name__, 'dir [%s] not exist.' % (srcDir,))
def clean(srcDir):
if os.path.exists(srcDir) and os.path.isdir(srcDir):
files = os.listdir(srcDir)
if len(files) > 0:
for i,f in enumerate(files):
filePath = os.path.join(srcDir, f)
if (os.path.isfile(filePath)):
try:
DuoPdf.cleanPdf(filePath, filePath)
except:
Log.w(DuoPdf.__name__, 'clean [%s] failed' % (filePath))
traceback.print_exc()
else:
Log.i(DuoPdf.__name__, 'skip file [%s]' % (filePath,))
else:
Log.w(DuoPdf.__name__, 'no file in [%s] to clean' % (srcDir))
else:
Log.w(DuoPdf.__name__, 'dir [%s] not exist.' % (srcDir,))
